Active Sensing-Driven Deep Learning for Robust XL-MIMO Hybrid Precoding
IEEE Transactions on Wireless Communications · 2026 · 25 · 25597-25613
DOI: 10.1109/twc.2026.3746482 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Wireless Communications, 2026. Verfasst von Yin Fang und 6 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Gefördert von: National Science and Technology Major Project of China, Natural Science Foundation on Frontier Leading Technology Basic Research Project of Jiangsu, National Natural Science Foundation of China.
Abstract (Originalsprache)
Near-field extremely large-scale multiple-input multiple-output (XL-MIMO) channels are characterized by spherical wavefront propagation and spatial non-stationarity. These characteristics cause significant performance degradation in angular-domain codebook-based schemes due to basis mismatch, while simultaneously introducing more effective degrees-of-freedoms (EDoFs). To fully exploit these EDoFs, this paper proposes an active sensing framework for time-division duplex point-to-point XL-MIMO systems to enable efficient hybrid precoding without explicit channel state information. By exchanging multi-round ping-pong pilots, the receiver aggregates low-dimensional observations into a continuous hidden state using a closed-form continuous-time neural network, achieving robust temporal feature extraction under noise. Based on the learned state, a Chebyshev polynomial-based Kolmogorov-Arnold network provides an expressive mapping from the hidden state to beamformers. Furthermore, QR decomposition, adaptive attention fusion, and an off-diagonal suppression objective are jointly integrated to stabilize multi-beam learning and encourage alignment with the channel’s dominant singular vectors. Simulation results demonstrate that the proposed framework maintains near-optimal spectral efficiency even at a low signal-to-noise ratio of −10 dB or under out-of-distribution channel conditions, while the learned beams exhibit minimal power leakage and strong interpretability.
Förderung
- National Science and Technology Major Project of China
- Natural Science Foundation on Frontier Leading Technology Basic Research Project of Jiangsu
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
- National Key Research and Development Program of China
- Top-Ten Technological Projects for Hunan Province in 2025
Zitieren
APA
Fang, Y., Xu, S., Fang, P., He, S., Li, C., Huang, Y., & Yang, L. (2026). Active Sensing-Driven Deep Learning for Robust XL-MIMO Hybrid Precoding. IEEE Transactions on Wireless Communications, 25, 25597-25613. https://doi.org/10.1109/twc.2026.3746482
Vancouver
Fang Y, Xu S, Fang P, He S, Li C, Huang Y, et al. Active Sensing-Driven Deep Learning for Robust XL-MIMO Hybrid Precoding. IEEE Transactions on Wireless Communications. 2026;25:25597-25613. doi:10.1109/twc.2026.3746482
BibTeX
@article{Fang2026,
author = {Fang, Yin and Xu, Shu and Fang, Pan and He, Shiwen and Li, Chunguo and Huang, Yongming and Yang, Luxi},
title = {Active Sensing-Driven Deep Learning for Robust XL-MIMO Hybrid Precoding},
journal = {IEEE Transactions on Wireless Communications},
year = {2026},
volume = {25},
pages = {25597--25613},
doi = {10.1109/twc.2026.3746482}
}
EUVIMED